AKTU · B.Tech · Important questions
AKTU Natural Language Processing Important Questions
The questions AKTU asks again and again in Natural Language Processing, found by comparing every question in 11 previous year papers from 2021-22 to 2025-26 (subject codes BCAI052, BOE089, KAI052, KCS072, KOE088).
How this list is made: we compared all 269 questions in these papers and grouped the ones that ask about the same thing. Each item shows how many papers it appeared in, which years, and other ways it was worded. Topics that come back often are a strong hint, not a guarantee, so study your full syllabus too.
Most repeated long questions
From Sections B and C (7 or 10 marks, depending on the year). Unit numbers come from Section C, where each question covers one unit.
- Discuss and Compare Top-Down and Bottom-Up parsing techniques. Explain with an example.
- Write down the bottom up chart parsing algorithm also explain with suitable example.
- Differentiate between Bottom-up and Top-down parsing. What algorithms are used for each of these types of parsing?
- What is Parsing? Differentiate between Top Down and Bottom Up parsing. Write the advantages and disadvantages of Top Down and Bottom Up parsing used in NLP.
- Explain hidden Markov model with Baum-Welch parameter re-estimation. Also elaborate on its implementation issues.
- Discuss the concept of probabilistic context free grammar in detail
- Discuss in brief about the concept of Probabilistic Context-Free Grammars.
- Discuss the process of handling questions in context free grammar. Explain with suitable example.
- Describe in detail about Handling questions in Context-Free Grammars.
- Explain the different steps in natural language understanding in detail.
- Mention about the Organization of Natural language Understanding Systems.
- Discuss about the database interface under the Natural Language Understanding.
- Explain the different techniques of knowledge representation.
- Explain how knowledge representation techniques are used in database interfaces.
- What do you mean by knowledge representation? Discuss about the semantics and knowledge representation in NLP.
- Explore the Linear Predictive Coding method in speech processing. How does LPC model speech signals, and what are its advantages in speech analysis and synthesis?
- Explore the Linear Predictive Coding method in speech processing. How 10 does LPC model speech signals, and what are its advantages in speech analysis and synthesis?
- Explain the Linear Predictive Coding (LPC) method in speech processing? How does LPC model speech signals, and what benefits does it offer in speech analysis and synthesis?
- Provide a pseudo-code algorithm for parsing a finite-state transducer and explain it with an example.
- Write an algorithm for parsing a finite-state transducer using the pseudo code. Explain the algorithm with an example.
- Analyze the challenges associated with accurately representing and 10 classifying speech sounds. How do these challenges impact the development of speech recognition systems?
- Compare and contrast Dependency Grammar with Phrase Structure 10 Grammar. Highlight the key differences in representing syntactic relationships between words in these two grammatical frameworks.
- Compare and contrast WSD techniques using dictionaries and thesauri. How do these lexical resources contribute to disambiguating word senses, and what are the considerations when choosing between them?
- Compare and contrast first-order logic with propositional logic. Discuss 10 the expressive power of first-order logic and its significance in representing complex relationships.
- Define Articulatory Phonetics. Also explain production and classification of speech sounds in detail. Give examples.
- Describe Feature Systems and Augmented Grammar under Grammars and Parsing.
- Describe about the Augmented Transition Networks.
- What are Augmented Transition Networks? How ATNs work? Write advantages and applications of ATN.
- Describe in detail about the Machine Translation.
- Discuss the role of semantic analysis in machine translation. How does semantic ambiguity affect translation quality? Explain with example.
- Describe in detail about the Movement Phenomenon in Language.
- Elaborate Movement phenomenon in language . Discuss the different types of movement.
- Discuss Probabilistic CYK parsing and Probabilistic Lexicalized CFGs. How do these probabilistic parsing techniques improve upon traditional parsing algorithms, and what are their applications in natural language processing?
- Discuss about the following: I. Transition Network Grammars. II. Top- Down Chart Parsing.
- Discuss different types of knowledge.
- Discuss knowledge. Explain the different types of knowledge.
- Discuss the challenges associated with evaluating N-grams and the role 10 of smoothing techniques.
- What are N-grams, and how are unsmoothed N-grams used in language 10 modeling? Discuss the challenges associated with evaluating N-grams and the role of smoothing techniques.
- Elaborate on the concept of time alignment in speech analysis, focusing 10 on the techniques of Dynamic Time Warping and the representation of multiple time-alignment paths.
- Examine how thesaurus-based and distributional methods contribute to 10 measuring word similarity. Discuss the strengths and weaknesses of each approach and their applicability in different contexts.
- Explain Augmented Grammars and Lexicon in the context of NLP.
- What is Augmented Grammars? Why use Augmented Grammars in NLP? Discuss in detail.
- Explain Viterbi Search Algorithm with an example.
Most repeated short questions (2 marks)
From Section A. Learn a crisp definition plus one example or line of explanation for each.
- Discuss the applications of filter bank methods in speech signal processing
- How does natural language understanding work?
- Define the term Natural Language.
- What is Natural Language Understanding? Write its key components.
- What are the Applications of Natural Language Processing (NLP)?
- Write any four applications of Natural Language Processing.
- What is Natural Language Processing (NLP)? Write the applications of NLP.
- Briefly describe knowledge representation.
- Discuss the concept of Knowledge Representation and Knowledge Base.
- Can you explain the challenges associated with language modeling in NLP?
- Describe the role of Perceptual Linear Prediction.
- Differentiate between top down and bottom-up parsers.
- What is the concept of Top-Down and Bottom-Up Parsers?
- Discuss Auxiliary verb with suitable example.
- Discuss about the concept of knowledge.
- Discuss pragmatic analysis.
- Discuss strategies for handling ambiguity in parsing.
- Discuss the limitations of supervised approaches in handling WSD challenges.
- Explain Context Free Grammars.
- What are the limitations of Probabilistic Context-Free Grammars (PCFGs)?
- Explain Frequency and Amplitude
- Explain Language Modelling.
- Explain TF and IDF
- How Dynamic Programming is employed in parsing algorithms?
- How do filter banks contribute to speech analysis?
- How do semantic attachments contribute to disambiguating word senses?
- How does the process of feature extraction contribute to understanding speech patterns?
Unit-wise questions from recent papers
Section C questions from the latest papers (2025-26 BOE089, 2024-25 KOE088, 2024-25 BCAI052), sorted by unit. Use these to practise one unit at a time.
Unit 1
- Discuss and Compare Top-Down and Bottom-Up parsing techniques. Explain with an example. (2025-26, BOE089)
- Explain the Transition Network Grammars. How do they differ from traditional context-free grammars? (2025-26, BOE089)
- Provide a pseudo-code algorithm for parsing a finite-state transducer and explain it with an example. (2024-25, BCAI052)
- What is Zipf's Law, and how is it applied in Natural Language Processing (NLP) (2024-25, BCAI052)
- What is Augmented Grammars? Why use Augmented Grammars in NLP? Discuss in detail. (2024-25, KOE088)
- What is Parsing? Differentiate between Top Down and Bottom Up parsing. Write the advantages and disadvantages of Top Down and Bottom Up parsing used in NLP. (2024-25, KOE088)
Unit 2
- Discuss about the role of morphological analysis and lexicon in Feature Systems and Augmented Grammars. (2025-26, BOE089)
- Explain the role of auxiliary verbs and verb phrases in English grammar. How are they represented in natural language grammars? (2025-26, BOE089)
- Explain Augmented Grammars and Lexicon in the context of NLP. (2024-25, BCAI052)
- For the CFGs given: S → NP VP VP → V NP NP → Det N Draw the shift-reduce parser in processing the sentence The woman saw a puppy Use the following lexical entries to create the chart parser. The | a: Det woman | puppy: N saw : V (2024-25, BCAI052)
- What are Augmented Transition Networks? How ATNs work? Write advantages and applications of ATN. (2024-25, KOE088)
- What is morphological analysis? What are the techniques used in morphological analysis for NLP? Write importance and applications of morphological analysis. (2024-25, KOE088)
Unit 3
- Discuss the movement phenomenon in natural language. How do these transformations affect sentence structure? (2025-26, BOE089)
- Discuss the concepts of encoding uncertainty in parsing. Compare probabilistic and deterministic parsing also write their advantages and limitations. (2025-26, BOE089)
- Explain the different relationships between word senses. Additionally, discuss the various knowledge sources used in Word Sense Disambiguation (WSD). (2024-25, BCAI052)
- Explain the concept of Thematic Roles for semantic analysis along with their application. (2024-25, BCAI052)
- What is Context-Free Grammars (CFGs)? Discuss about the different types of grammars used in NLP. (2024-25, KOE088)
- What is an Auxiliary Verb? Discuss about the different types of Auxiliary Verbs. How to use Auxiliary Verbs explain with the help of an example? (2024-25, KOE088)
Unit 4
- Explain the concept of ambiguity in natural language processing. Discuss about the different types of ambiguity. (2025-26, BOE089)
- Discuss the fundamentals of probabilistic language processing. How are probabilities estimated in NLP? (2025-26, BOE089)
- Explain the vowels, semi vowels, diphthongs and consonants in respect of Speech recognition system. (2024-25, BCAI052)
- Explain the Linear Predictive Coding (LPC) method in speech processing? How does LPC model speech signals, and what benefits does it offer in speech analysis and synthesis? (2024-25, BCAI052)
- What do you mean by ambiguity and uncertainty in human language? Discuss about the major challenges of NLP. (2024-25, KOE088)
- What are the statistics used for NLP? Discuss about the various Neural Network models used for NLP. (2024-25, KOE088)
Unit 5
- Discuss the process of Part-of-Speech tagging. How are lexical probabilities obtained and used in probabilistic tagging models? (2025-26, BOE089)
- Explain Probabilistic Context-Free Grammars (PCFGs). Discuss the role of Best-First Parsing in selecting the most likely parse. (2025-26, BOE089)
- Explain hidden Markov model with Baum-Welch parameter re- estimation. Also elaborate on its implementation issues. (2024-25, BCAI052)
- Illustrate the concept and process of Chatbots in detail with any example. (2024-25, BCAI052)
- What are Probabilistic Models? What are the different types of Probabilistic Models? Write importance and applications of Probabilistic Models. (2024-25, KOE088)
- Define Probabilistic Context Free Grammar (PCFG). Write CKY parsing algorithm. How to calculate the probability of a parse tree in PCFG? (2024-25, KOE088)
Papers used for this list
- AKTU Natural Language Processing (BOE089) question paper 2025-26
- AKTU Natural Language Processing (BCAI052) question paper 2024-25
- AKTU Natural Language Processing (KCS072) question paper 2024-25
- AKTU Natural Language Processing (KOE088) question paper 2024-25
- AKTU Natural Language Processing (KAI052) question paper 2023-24
- AKTU Natural Language Processing (KCS072) question paper 2023-24
- AKTU Natural Language Processing (KOE088) question paper 2023-24
- AKTU Natural Language Processing (KAI052) question paper 2022-23
- AKTU Natural Language Processing (KCS072) question paper 2022-23
- AKTU Natural Language Processing (KOE088) question paper 2022-23
- AKTU Natural Language Processing (KOE088) question paper 2021-22
How to use these questions
- Start with the questions asked in the most papers, and make short notes for each.
- Write 2–3 long answers by hand with a timer (about 12–15 minutes each), then compare them with your textbook.
- Revise all the 2-mark questions the night before the exam.
- Finish with one full paper from the list above, timed.
Full plan with AI prompts: How to prepare for AKTU exams using previous year papers. After results, check your marks with the AKTU CGPA calculator.
Frequently asked questions
Are these AKTU Natural Language Processing questions guaranteed to come in the exam?
No. They are the questions that repeated most in past papers, which makes them a strong hint, but AKTU can ask anything from the syllabus. Use this list to prioritise, not to skip units.
How was this important questions list made?
We compared all 269 questions from 11 AKTU Natural Language Processing papers (2021-22 to 2025-26) and grouped questions that ask about the same topic, then counted how many papers each appeared in.
Where can I download AKTU Natural Language Processing previous year papers?
Every paper used here is on LearnAIFast with all questions as text and a link to the original PDF. See the list of papers above.
More subjects: all AKTU important questions · all question papers